Path to Astra: critical capabilities and frontier safeguards
Highlights OpenAI's progress in developing secure, advanced AI models with built-in safety measures, relevant for anyone tracking AI capabilities and governance.
AI Summary
OpenAI announces Astra, its first model to meet the critical cybersecurity capability threshold under its Preparedness Framework with enhanced safeguards.
Excerpt
Astra is the first OpenAI model to meet the Critical cybersecurity capability threshold under the Preparedness Framework, with stronger safeguards for release.
